Cover Image

Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pang, Jiacheng, Chaubey, Ashutosh, Soleymani, Mohammad
Format:	Preprint
Published:	2026
Subjects:	Sound Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization
by: Chaubey, Ashutosh, et al.
Published: (2026)

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
by: Chaubey, Ashutosh, et al.
Published: (2026)

DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion
by: Siniukov, Maksim, et al.
Published: (2025)

Listenable Maps for Audio Classifiers
by: Paissan, Francesco, et al.
Published: (2024)

Detecting and Mitigating Insertion Hallucination in Video-to-Audio Generation
by: Chen, Liyang, et al.
Published: (2025)

NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
by: Liao, Huan, et al.
Published: (2025)

Investigating Modality Contribution in Audio LLMs for Music
by: Morais, Giovana, et al.
Published: (2025)

Listenable Maps for Zero-Shot Audio Classifiers
by: Paissan, Francesco, et al.
Published: (2024)

Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Bias
by: Fursule, Aishwarya, et al.
Published: (2026)

Learning When to Think While Listening in Large Audio-Language Models
by: Song, Zhiyuan, et al.
Published: (2026)

ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech
by: Lou, Haowei, et al.
Published: (2026)

Adaptive Discovery of Interpretable Audio Attributes with Multimodal LLMs for Low-Resource Classification
by: Yoshimura, Kosuke, et al.
Published: (2026)

Thinking While Listening: Simple Test Time Scaling For Audio Classification
by: Verma, Prateek, et al.
Published: (2025)

LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
by: Du, Zhihao, et al.
Published: (2023)

How to Label Resynthesized Audio: The Dual Role of Neural Audio Codecs in Audio Deepfake Detection
by: Xiao, Yixuan, et al.
Published: (2026)

VoxSafeBench: Not Just What Is Said, but Who, How, and Where
by: Wang, Yuxiang, et al.
Published: (2026)

VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis
by: Lin, Weiwei, et al.
Published: (2024)

ADNAC: Audio Denoiser using Neural Audio Codec
by: Jimon, Daniel, et al.
Published: (2025)

Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration
by: Sun, Esther, et al.
Published: (2026)

Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
by: Wu, Daiqing, et al.
Published: (2026)

Do Foundational Audio Encoders Understand Music Structure?
by: Toyama, Keisuke, et al.
Published: (2025)

Do Audio-Language Models Understand Linguistic Variations?
by: Selvakumar, Ramaneswaran, et al.
Published: (2024)

AUDETER: A Large-scale Dataset for Deepfake Audio Detection in Open Worlds
by: Wang, Qizhou, et al.
Published: (2025)

Virtual Consistency for Audio Editing
by: Cervera, Matthieu, et al.
Published: (2025)

PACE: Pretrained Audio Continual Learning
by: Li, Chang, et al.
Published: (2026)

Segmentwise Pruning in Audio-Language Models
by: Gibier, Marcel, et al.
Published: (2025)

Adapting Neural Audio Codecs to EEG
by: Kastrati, Ard, et al.
Published: (2025)

Human Brain Exhibits Distinct Patterns When Listening to Fake Versus Real Audio: Preliminary Evidence
by: Salehi, Mahsa, et al.
Published: (2024)

APEX: Audio Prototype EXplanations for Classification Tasks
by: Kawa, Piotr, et al.
Published: (2026)

Audio Super-Resolution with Latent Bridge Models
by: Li, Chang, et al.
Published: (2025)

Structured-Noise Masked Modeling for Video, Audio and Beyond
by: Bhowmik, Aritra, et al.
Published: (2025)

Can Masked Autoencoders Also Listen to Birds?
by: Rauch, Lukas, et al.
Published: (2025)

Training-Free Multimodal Guidance for Video to Audio Generation
by: Grassucci, Eleonora, et al.
Published: (2025)

Semantic-Aware Confidence Calibration for Automated Audio Captioning
by: Dunker, Lucas, et al.
Published: (2025)

FastWave: Optimized Diffusion Model for Audio Super-Resolution
by: Kuznetsov, Nikita, et al.
Published: (2026)

Audio-Visual Continual Test-Time Adaptation without Forgetting
by: Maharana, Sarthak Kumar, et al.
Published: (2026)

Transformer Based Machine Fault Detection From Audio Input
by: Holla, Kiran Voderhobli
Published: (2026)

TADA! Tuning Audio Diffusion Models through Activation Steering
by: Staniszewski, Łukasz, et al.
Published: (2026)

Unleashing the Power of Natural Audio Featuring Multiple Sound Sources
by: Cheng, Xize, et al.
Published: (2025)

Improving Audio Classification by Transitioning from Zero- to Few-Shot
by: Taylor, James, et al.
Published: (2025)